Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue in a serious context

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating justification or concern about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    defense
    -1.07
    avored
    -0.96
     favors
    -0.91
    bors
    -0.86
    colored
    -0.86
     favored
    -0.86
    rollment
    -0.85
    Defense
    -0.83
     favor
    -0.82
    WASHINGTON
    -0.82
    POSITIVE LOGITS
     realise
    1.58
     recognise
    1.54
     paed
    1.48
     apologise
    1.46
     realised
    1.44
     recognised
    1.43
     civilisation
    1.41
     £
    1.39
     apologised
    1.38
     organise
    1.38
    Act Density 1.172%

    No Known Activations